© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 120738
    Prev
    Next
    INDEX
    Explanations

    All

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dealings
    -0.07
    ά
    -0.07
    �
    -0.06
     enumerable
    -0.06
    imitive
    -0.06
    utin
    -0.06
    olate
    -0.06
     purported
    -0.06
    trust
    -0.06
    .s
    -0.06
    POSITIVE LOGITS
     모든
    0.09
    onent
    0.06
     ※
    0.06
    chron
    0.06
    εδ
    0.06
     دریافت
    0.06
    +'_
    0.06
    gunakan
    0.06
    abbreviation
    0.06
     Annotation
    0.06
    Activations Density 0.003%

    No Known Activations